GLM Z1 32B 0414 — Hardware Requirements & GPU Compatibility
Chat
GLM Z1 32B 0414 is a 32.6B-parameter open language model from Z.ai in the GLM family. It supports a context window of up to 32,768 tokens. At Q4_K_M it needs about 19.97 GB of VRAM — see which GPUs and Macs can run it below.
41.2K downloads
196 likesSpecifications
- Publisher
- Z.ai
- Family
- GLM
- Parameters
- 32.6B
- Architecture
- Glm4ForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 151,552
- Release Date
- 2025-04-08
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does GLM Z1 32B 0414 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 14.3 GB | 16.2 GB | 13.84 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 16.3 GB | 18.2 GB | 15.88 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 20.0 GB | 21.9 GB | 19.54 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 23.6 GB | 25.6 GB | 23.20 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 27.3 GB | 29.2 GB | 26.87 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 33.0 GB | 34.9 GB | 32.57 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 65.6 GB | 67.5 GB | 65.13 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run GLM Z1 32B 0414?
Q4_K_M · 20.0 GBGLM Z1 32B 0414 (Q4_K_M) requires 20.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 26+ GB is recommended. Using the full 33K context window can add up to 1.9 GB, bringing total usage to 21.9 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run GLM Z1 32B 0414?
Q4_K_M · 20.0 GB41 devices with unified memory can run GLM Z1 32B 0414, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does GLM Z1 32B 0414 need?
GLM Z1 32B 0414 requires 20.0 GB of VRAM at Q4_K_M, or 65.6 GB at BF16. Full 33K context adds up to 1.9 GB (21.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 32.6B × 4.8 bits ÷ 8 = 19.5 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 2.4 GB (at full 33K context)
VRAM usage by quantization
Q4_K_M20.0 GBQ4_K_M + full context21.9 GB- Can NVIDIA GeForce RTX 4090 run GLM Z1 32B 0414?
Yes, at Q5_K_M (23.6 GB) or lower. Higher quantizations like Q6_K (27.3 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for GLM Z1 32B 0414?
For GLM Z1 32B 0414, Q4_K_M (20.0 GB) offers the best balance of quality and VRAM usage. Q5_K_M (23.6 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 14.3 GB.
VRAM requirement by quantization
Q2_K14.3 GBQ4_K_M ★20.0 GBQ5_K_M23.6 GBQ6_K27.3 GBQ8_033.0 GBBF1665.6 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run GLM Z1 32B 0414 on a Mac?
GLM Z1 32B 0414 requires at least 14.3 GB at Q2_K, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run GLM Z1 32B 0414 locally?
Yes — GLM Z1 32B 0414 can run locally on consumer hardware. At Q4_K_M quantization it needs 20.0 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is GLM Z1 32B 0414?
At Q4_K_M, GLM Z1 32B 0414 can reach ~240 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~33 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 20.0 × 0.65 = ~260 tok/s
Estimated speed at Q4_K_M (20.0 GB)
~260 tok/s~33 tok/s~260 tok/s~240 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of GLM Z1 32B 0414?
At Q4_K_M, the download is about 19.54 GB. The full-precision BF16 version is 65.13 GB. The smallest option (Q2_K) is 13.84 GB.
- Which GPUs can run GLM Z1 32B 0414?
8 consumer GPUs can run GLM Z1 32B 0414 at Q4_K_M (20.0 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run GLM Z1 32B 0414?
41 devices with unified memory can run GLM Z1 32B 0414 at Q4_K_M (20.0 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.